Nemotron-4 15B Technical Report

Hanlin Tang is a researcher at Cohere. His public page says his work focuses on foundation models, large language model post-training, reinforcement learning, and vision-language or language-model agents, and that he previously held research internships at NVIDIA and the Vector Institute.

Sanjiv Kumar is a Google Fellow and vice president at Google Research. His public homepage says he leads teams working on large machine learning foundation models and generative AI, has spent more than 25 years building machine learning systems and products, and received a PhD in computer science from Carnegie Mellon University in 2005.

Prasanna Parthasarathi is a research scientist at Huawei Noah's Ark Lab in Montreal. His public speaker and lab-profile pages say he collaborates with Mila and McGill University, works on natural language processing, dialogue systems, and social simulation, and completed a PhD at McGill University in 2022 under Joelle Pineau.

Boris Ginsburg is a principal engineer and research scientist at NVIDIA whose work focuses on efficient machine learning and deep learning for speech recognition, language processing, and computer vision.

Dilek Hakkani-Tur is a Professor of Computer Science at the University of Illinois Urbana-Champaign and an Amazon Scholar at Amazon Health Science. Her UIUC faculty profile says her research interests include conversational AI, natural language and speech processing, spoken dialogue systems, and machine learning for language processing.

Vice President of Applied Deep Learning Research at NVIDIA, leading work on conversational AI, generative AI, and accelerated deep learning software.

Public report authorship links Saurav Muralidharan to the Nemotron-4 15B Technical Report at NVIDIA.

Public report authorship links Prathyusha Kamesetty to the Nemotron-4 15B Technical Report at NVIDIA.

Member of technical staff at NVIDIA Research focused on language models, deep learning, and efficient training systems.

Research scientist on the AllenNLP team at the Allen Institute for AI, where his homepage highlights work on open language models such as OLMo and Tulu and a focus on post-training language models.

Research scientist at NVIDIA with publications in machine learning and embodied AI.

Researcher at OpenAI focused on data-centric methods for foundation models, including synthetic data and reinforcement learning. Previously a research scientist at Meta GenAI; earned BS, MS, and PhD degrees in computer science at Stanford.

Public report authorship links Ali Payani to the OLMoE: Open Mixture-of-Experts Language Models at Ai2.

Research scientist at NVIDIA.

Public report authorship links Mohit Bansal to the Nemotron-4 15B Technical Report at NVIDIA.

Dragomir Radev is an Eminent Professor of natural language processing at MBZUAI. His research spans NLP, information retrieval, question answering, and summarization, and he is also a coauthor of the Nemotron-4 15B technical report.

Public report authorship links Yejin Choi to the Nemotron-4 15B Technical Report at NVIDIA.

Public report authorship links Michael Flaherty to the Nemotron-4 15B Technical Report at NVIDIA.

Public report authorship links Jianfeng Gao to the Nemotron-4 15B Technical Report at NVIDIA.

Canonical link

Hanlin Tang

Sanjiv Kumar

Prasanna Parthasarathi

Boris Ginsburg

Dilek Hakkani-Tur

Bryan Catanzaro

Saurav Muralidharan

Prathyusha Kamesetty

Pramod Kumbhare

Pradeep Dasigi

Carlos E. Jimenez

Sang Michael Xie

Ali Payani

Rajarshi Das

Mohit Bansal

Dragomir Radev

Yejin Choi

Michael Flaherty

Jianfeng Gao